StudyBrixFree worksheets, study guides and courses

Artificial intelligence · Grades 9–12

Examples, features, labels and data quality

An example is one unit of observation. Features are inputs available at prediction time; a label is the target used for supervised learning.

Make a worksheet

Prerequisites

Tables, categories and averages.

Study notes

Records

An example is one unit of observation. Features are inputs available at prediction time; a label is the target used for supervised learning.

Quality

Missing values, inconsistent units, duplicate records and ambiguous labels can distort learning. Cleaning choices need documentation.

Leakage

Information from the target or future must not enter features when it would be unavailable during actual prediction. Splits must respect linked records and time.

Privacy

Use authorized, appropriate data and minimize personal information. Synthetic examples in this course do not require uploading personal records.

Worked examples

In supervised learning, what is a label?

Labels specify what the model is trained to predict.

The target output for an example

Which feature leaks future information when predicting tomorrow's sales today?

The final target would not be known at prediction time.

Tomorrow's final sales total

Check your understanding

  1. A table has 200 records and 10 exact duplicates to remove. How many records remain?

  2. What should be recorded when converting metres to centimetres in a feature?

    1. Only a model name
    2. Nothing if the numbers look bigger
    3. Only a new file colour
    4. The transformation and resulting units

  3. Why can two rows from the same person in both train and test sets distort evaluation?

  4. Of 80 records, 20 lack a given feature. Find its missing fraction.

Answers and marking guidance

Answers and marking notes
  1. 190

    Subtract removed records from total records.

  2. The transformation and resulting units

    Units and transformations affect interpretation and reproducibility.

  3. The model may exploit person-specific information shared across splits. Evaluation can become easier than generalizing to new people.

    Credit linked records and a split matched to deployment.

  4. 0.25

    20/80=0.25.

Further reading and review references

These are reference links, not copied exercises, institutional endorsement or proof of independent review.

AI-assisted preview; independent educational review required. Level labels describe prerequisites, not accreditation or official curriculum alignment.